All skills
browser-automation
Drives the built-in browser or your own Chrome to open pages, click, type and extract data while signed in.
- Part of Prism-Shadow/penguin-harness
- AI Engineering · App control
More App control skills
See all- browser-use100kDrives a real browser to automate pages, scrape data, take screenshots and test sites.
- agent-device21.6kDrives iOS, Android, HarmonyOS, and TV apps on devices and simulators: tapping, typing, scrolling, screenshots, and installing builds.
- dogfood13.2kExplores a mobile app on iOS or Android to hunt for bugs and UX problems and report what it finds.
- remote-browser5kControls an isolated cloud browser from a sandboxed machine using the Browser Use CLI.
Also in this pack
- humanizer2Rewrites or edits prose in any language so it reads like edited human writing rather than default AI output.
- ollama2Deploys and serves local models with Ollama and exposes an OpenAI-compatible endpoint to apps and agents.
- vllm2Deploys and serves language models with vLLM behind an OpenAI-compatible endpoint with tool calling.
- agent-evaluation1Runs one test agent on one benchmark case once, scores it privately and returns a single protocol result.